Merge tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a major amount of change, the i915 trees got split into display
  and gt trees to better facilitate higher level review, and there's a
  major refactoring of i915 GEM locking to use more core kernel concepts
  (like ww-mutexes). msm gets per-process pagetables, older AMD SI cards
  get DC support, nouveau got a bump in displayport support with common
  code extraction from i915.

  Outside of drm this contains a couple of patches for hexint
  moduleparams which you've acked, and a virtio common code tree that
  you should also get via it's regular path.

  New driver:
   - Cadence MHDP8546 DisplayPort bridge driver

  core:
   - cross-driver scatterlist cleanups
   - devm_drm conversions
   - remove drm_dev_init
   - devm_drm_dev_alloc conversion

  ttm:
   - lots of refactoring and cleanups

  bridges:
   - chained bridge support in more drivers

  panel:
   - misc new panels

  scheduler:
   - cleanup priority levels

  displayport:
   - refactor i915 code into helpers for nouveau

  i915:
   - split into display and GT trees
   - WW locking refactoring in GEM
   - execbuf2 extension mechanism
   - syncobj timeline support
   - GEN 12 HOBL display powersaving
   - Rocket Lake display additions
   - Disable FBC on Tigerlake
   - Tigerlake Type-C + DP improvements
   - Hotplug interrupt refactoring

  amdgpu:
   - Sienna Cichlid updates
   - Navy Flounder updates
   - DCE6 (SI) support for DC
   - Plane rotation enabled
   - TMZ state info ioctl
   - PCIe DPC recovery support
   - DC interrupt handling refactor
   - OLED panel fixes

  amdkfd:
   - add SMI events for thermal throttling
   - SMI interface events ioctl update
   - process eviction counters

  radeon:
   - move to dma_ for allocations
   - expose sclk via sysfs

  msm:
   - DSI support for sm8150/sm8250
   - per-process GPU pagetable support
   - Displayport support

  mediatek:
   - move HDMI phy driver to PHY
   - convert mtk-dpi to bridge API
   - disable mt2701 tmds

  tegra:
   - bridge support

  exynos:
   - misc cleanups

  vc4:
   - dual display cleanups

  ast:
   - cleanups

  gma500:
   - conversion to GPIOd API

  hisilicon:
   - misc reworks

  ingenic:
   - clock handling and format improvements

  mcde:
   - DSI support

  mgag200:
   - desktop g200 support

  mxsfb:
   - i.MX7 + i.MX8M
   - alpha plane support

  panfrost:
   - devfreq support
   - amlogic SoC support

  ps8640:
   - EDID from eDP retrieval

  tidss:
   - AM65xx YUV workaround

  virtio:
   - virtio-gpu exported resources

  rcar-du:
   - R8A7742, R8A774E1 and R8A77961 support
   - YUV planar format fixes
   - non-visible plane handling
   - VSP device reference count fix
   - Kconfig fix to avoid displaying disabled options in .config"

* tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm: (1494 commits)
  drm/ingenic: Fix bad revert
  drm/amdgpu: Fix invalid number of character '{' in amdgpu_acpi_init
  drm/amdgpu: Remove warning for virtual_display
  drm/amdgpu: kfd_initialized can be static
  drm/amd/pm: setup APU dpm clock table in SMU HW initialization
  drm/amdgpu: prevent spurious warning
  drm/amdgpu/swsmu: fix ARC build errors
  drm/amd/display: Fix OPTC_DATA_FORMAT programming
  drm/amd/display: Don't allow pstate if no support in blank
  drm/panfrost: increase readl_relaxed_poll_timeout values
  MAINTAINERS: Update entry for st7703 driver after the rename
  Revert "gpu/drm: ingenic: Add option to mmap GEM buffers cached"
  drm/amd/display: HDMI remote sink need mode validation for Linux
  drm/amd/display: Change to correct unit on audio rate
  drm/amd/display: Avoid set zero in the requested clk
  drm/amdgpu: align frag_end to covered address space
  drm/amdgpu: fix NULL pointer dereference for Renoir
  drm/vmwgfx: fix regression in thp code due to ttm init refactor.
  drm/amdgpu/swsmu: add interrupt work handler for smu11 parts
  drm/amdgpu/swsmu: add interrupt work function
  ...

1 files changed, 206 insertions, 2 deletions

diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 3a381a9674c9..22ac7c692a81 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -4,15 +4,210 @@
  * Author: Rob Clark <robdclark@gmail.com>
  */
 
+#include <linux/adreno-smmu-priv.h>
+#include <linux/io-pgtable.h>
 #include "msm_drv.h"
 #include "msm_mmu.h"
 
 struct msm_iommu {
 	struct msm_mmu base;
 	struct iommu_domain *domain;
+	atomic_t pagetables;
 };
+
 #define to_msm_iommu(x) container_of(x, struct msm_iommu, base)
 
+struct msm_iommu_pagetable {
+	struct msm_mmu base;
+	struct msm_mmu *parent;
+	struct io_pgtable_ops *pgtbl_ops;
+	phys_addr_t ttbr;
+	u32 asid;
+};
+static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu)
+{
+	return container_of(mmu, struct msm_iommu_pagetable, base);
+}
+
+static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova,
+		size_t size)
+{
+	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+	struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
+	size_t unmapped = 0;
+
+	/* Unmap the block one page at a time */
+	while (size) {
+		unmapped += ops->unmap(ops, iova, 4096, NULL);
+		iova += 4096;
+		size -= 4096;
+	}
+
+	iommu_flush_iotlb_all(to_msm_iommu(pagetable->parent)->domain);
+
+	return (unmapped == size) ? 0 : -EINVAL;
+}
+
+static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova,
+		struct sg_table *sgt, size_t len, int prot)
+{
+	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+	struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
+	struct scatterlist *sg;
+	size_t mapped = 0;
+	u64 addr = iova;
+	unsigned int i;
+
+	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+		size_t size = sg->length;
+		phys_addr_t phys = sg_phys(sg);
+
+		/* Map the block one page at a time */
+		while (size) {
+			if (ops->map(ops, addr, phys, 4096, prot, GFP_KERNEL)) {
+				msm_iommu_pagetable_unmap(mmu, iova, mapped);
+				return -EINVAL;
+			}
+
+			phys += 4096;
+			addr += 4096;
+			size -= 4096;
+			mapped += 4096;
+		}
+	}
+
+	return 0;
+}
+
+static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
+{
+	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+	struct msm_iommu *iommu = to_msm_iommu(pagetable->parent);
+	struct adreno_smmu_priv *adreno_smmu =
+		dev_get_drvdata(pagetable->parent->dev);
+
+	/*
+	 * If this is the last attached pagetable for the parent,
+	 * disable TTBR0 in the arm-smmu driver
+	 */
+	if (atomic_dec_return(&iommu->pagetables) == 0)
+		adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL);
+
+	free_io_pgtable_ops(pagetable->pgtbl_ops);
+	kfree(pagetable);
+}
+
+int msm_iommu_pagetable_params(struct msm_mmu *mmu,
+		phys_addr_t *ttbr, int *asid)
+{
+	struct msm_iommu_pagetable *pagetable;
+
+	if (mmu->type != MSM_MMU_IOMMU_PAGETABLE)
+		return -EINVAL;
+
+	pagetable = to_pagetable(mmu);
+
+	if (ttbr)
+		*ttbr = pagetable->ttbr;
+
+	if (asid)
+		*asid = pagetable->asid;
+
+	return 0;
+}
+
+static const struct msm_mmu_funcs pagetable_funcs = {
+		.map = msm_iommu_pagetable_map,
+		.unmap = msm_iommu_pagetable_unmap,
+		.destroy = msm_iommu_pagetable_destroy,
+};
+
+static void msm_iommu_tlb_flush_all(void *cookie)
+{
+}
+
+static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
+		size_t granule, void *cookie)
+{
+}
+
+static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
+		unsigned long iova, size_t granule, void *cookie)
+{
+}
+
+static const struct iommu_flush_ops null_tlb_ops = {
+	.tlb_flush_all = msm_iommu_tlb_flush_all,
+	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
+	.tlb_flush_leaf = msm_iommu_tlb_flush_walk,
+	.tlb_add_page = msm_iommu_tlb_add_page,
+};
+
+struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
+{
+	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev);
+	struct msm_iommu *iommu = to_msm_iommu(parent);
+	struct msm_iommu_pagetable *pagetable;
+	const struct io_pgtable_cfg *ttbr1_cfg = NULL;
+	struct io_pgtable_cfg ttbr0_cfg;
+	int ret;
+
+	/* Get the pagetable configuration from the domain */
+	if (adreno_smmu->cookie)
+		ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie);
+	if (!ttbr1_cfg)
+		return ERR_PTR(-ENODEV);
+
+	pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL);
+	if (!pagetable)
+		return ERR_PTR(-ENOMEM);
+
+	msm_mmu_init(&pagetable->base, parent->dev, &pagetable_funcs,
+		MSM_MMU_IOMMU_PAGETABLE);
+
+	/* Clone the TTBR1 cfg as starting point for TTBR0 cfg: */
+	ttbr0_cfg = *ttbr1_cfg;
+
+	/* The incoming cfg will have the TTBR1 quirk enabled */
+	ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
+	ttbr0_cfg.tlb = &null_tlb_ops;
+
+	pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
+		&ttbr0_cfg, iommu->domain);
+
+	if (!pagetable->pgtbl_ops) {
+		kfree(pagetable);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/*
+	 * If this is the first pagetable that we've allocated, send it back to
+	 * the arm-smmu driver as a trigger to set up TTBR0
+	 */
+	if (atomic_inc_return(&iommu->pagetables) == 1) {
+		ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg);
+		if (ret) {
+			free_io_pgtable_ops(pagetable->pgtbl_ops);
+			kfree(pagetable);
+			return ERR_PTR(ret);
+		}
+	}
+
+	/* Needed later for TLB flush */
+	pagetable->parent = parent;
+	pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
+
+	/*
+	 * TODO we would like each set of page tables to have a unique ASID
+	 * to optimize TLB invalidation.  But iommu_flush_iotlb_all() will
+	 * end up flushing the ASID used for TTBR1 pagetables, which is not
+	 * what we want.  So for now just use the same ASID as TTBR1.
+	 */
+	pagetable->asid = 0;
+
+	return &pagetable->base;
+}
+
 static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
 		unsigned long iova, int flags, void *arg)
 {
@@ -36,7 +231,11 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 	size_t ret;
 
-	ret = iommu_map_sg(iommu->domain, iova, sgt->sgl, sgt->nents, prot);
+	/* The arm-smmu driver expects the addresses to be sign extended */
+	if (iova & BIT_ULL(48))
+		iova |= GENMASK_ULL(63, 49);
+
+	ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot);
 	WARN_ON(!ret);
 
 	return (ret == len) ? 0 : -EINVAL;
@@ -46,6 +245,9 @@ static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
+	if (iova & BIT_ULL(48))
+		iova |= GENMASK_ULL(63, 49);
+
 	iommu_unmap(iommu->domain, iova, len);
 
 	return 0;
@@ -78,9 +280,11 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain)
 		return ERR_PTR(-ENOMEM);
 
 	iommu->domain = domain;
-	msm_mmu_init(&iommu->base, dev, &funcs);
+	msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
 	iommu_set_fault_handler(domain, msm_fault_handler, iommu);
 
+	atomic_set(&iommu->pagetables, 0);
+
 	ret = iommu_attach_device(iommu->domain, dev);
 	if (ret) {
 		kfree(iommu);